INDEX

Explanations

titles or headings within a collection

oai_token-act-pair · gpt-3.5-turbo

instances of the article "a" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

livious

-0.80

alties

-0.73

anism

-0.70

enance

-0.68

ahu

-0.68

agues

-0.66

bots

-0.66

 agreements

-0.66

agents

-0.65

arenthood

-0.65

POSITIVE LOGITS

 rundown

1.50

 glimpse

1.37

 breakdown

1.30

 synopsis

1.26

 summary

1.24

 snapshot

1.22

 roundup

1.21

 list

1.18

 brief

1.18

 recap

1.16

Activations Density 0.158%

titles or headings within a collection

instances of the article "a" in various contexts

No Comments

No Known Activations